arXiv cs.AI· Aysenur Inan, Reza Yousefi Maragheh, Jayesh Uddhav Kudase, Selene Xu, Kaushiki Nag, Jianpeng Xu, Sushant Kumar·· 2 小时前AI 评分37
BehaveRec：长期行为历史何时有助于序列推荐？基于会话、历史与社区信号的研究
BehaveRec: When Does Long-Term Behavioral History Help Sequential Recommendation? A Study with Session, History, and Community Signals
AI 导读
BehaveRec 是一个结合因果会话 Transformer、90 天窗口双向用户历史编码器和基于 GraphSAGE 的用户图的序列推荐框架，通过可学习的门控融合三种信号。
正文 · 原文
Abstract:Sequential recommendation models typically predict a user's next action from recent session interactions, which limits personalization when short-term signals are weak or ambiguous. Rather than assuming that incorporating longer-term history and community signals is universally beneficial, we study when it actually helps. We propose BehaveRec, a three-signal framework combining a causal session transformer, a bidirectional User History Encoder over a 90-day window, and a GraphSAGE module over a user-user graph built from behavioral embedding similarity rather than item co-occurrence; a learned gate blends the three signals per user. On an industrial dataset of 137M sequences from 12.6M users, BehaveRec improves R@5 by +3.2% over SASRec, with a larger-capacity SASRec baseline (more parameters than BehaveRec) still trailing by +2.5%, ruling out capacity as the explanation. More importantly, a user-level stratification by history length reveals a clear dose-response relationship: BehaveRec's advantage is negligible below roughly 10 interactions and grows monotonically with history richness, reaching +0.017 R@5 for users with 101+ events. This pattern is corroborated across one industrial and three public datasets spanning history-rich to history-sparse regimes, where session-only models remain preferable. These headline results, and the resulting deployment threshold, are established for category-level intent prediction; a preliminary, single-run check on the full item-level vocabulary yields a directionally mixed result and is scoped as an open question rather than a claim. We use these results to derive a practical deployment rule -- roughly 20 interactions per user -- for when long-term history and behavioral-graph signals are worth their added complexity. Despite this added complexity, BehaveRec remains lightweight: it uses 5.67M parameters and trains on a single GPU in under two days.
| Subjects: | Artificial Intelligence (cs.AI); Information Retrieval (cs.IR) |
| Cite as: | arXiv:2610.36239 [cs.AI] |
| (or arXiv:2610.36239v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.36239 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Reza Yousefi Maragheh [view email]
[v1]
Mon, 26 Oct 2026 20:15:26 UTC (111 KB)
来源：arXiv cs.AI · arxiv.org